R Applications in Earth Sciences

This textbook helps to understand the real Earth data with the practical application of many handy R tools and techniques. R language and thousands of R packages can be used to solve the most sophisticated scientific problems. The book provides insights to the various approaches to Earth-related data analysis, starting from data preparation and validation, exploratory data analysis, linear regression, and going through time series decomposition, modeling, and prediction. In addition, the book introduces machine learning techniques and their application to some real problems. Along with a profound explanation of the datasets and theoretical considerations of the methods, the book offers a way of solving practical problems lying at the frontline of modern data analysis in physical geography, soils, and climate science.

Provides step-by-step tutorial on how to use R for practical data exploration and modeling Contains in-depth explanation of the complexity and applicability of various spatial data and time series Presents thorough explanation of statistical methods

Autorentext

ukasz Pawlik is a geographer, geomorphologist, and data scientist. His research encompasses abroad range of topics, from analyses of spatial and soil data, climate time series, geochemistry of fossil deposits, and radiocarbon dating. A majority of his projects and teaching activities at the university are heavily built on and supported by multiple R functionalities, including existing packages, custom functions, and R Markdown documents.

Inhalt

Chapter 1: Introduction.- Chapter 2: R for data science Functionality and basic concepts.- Chapter 3: Soil data structure, properties, and visualization.- Chapter 4: Geochemistry of fossil deposits and climate reconstructions based on proxy data.- Chapter 5: Climate time series.- Chapter 6: Geomorphic data and geomorphometry analyses.- Chapter 7: Dating the past with the radiocarbon method.- Chapter 8: Global tectonics and earthquake dynamics From data to visualization.- Chapter 9: Land and forest cover change mapping.- Chapter 10: Extreme climate event modeling and prediction with machine learning methods.- Chapter 11: Knowledge in the cloud LiDAR point cloud data.- Chapter 12: Dynamic visualization and animation.- Chapter 13: Final comments, conclusions, and data science perspective.